On Thu, 2018-12-06 at 22:18 +0800, Weiping Zhang wrote:
> Before this patch, even we set io_timeout to 30*HZ(default), but
> blk_rq_timeout always return jiffies +5*HZ,
> [1]. if there no pending request in timeout list, the timer callback
> blk_rq_timed_out_timer will be called after 5*HZ, and
Bart Van Assche 于2018年12月5日周三 下午11:59写道:
>
> On Wed, 2018-12-05 at 23:37 +0800, Weiping Zhang wrote:
> > @@ -130,7 +119,7 @@ void blk_add_timer(struct request *req)
> >* than an existing one, modify the timer. Round up to next nearest
> >* second.
> >*/
> > - expiry =
On Wed, 2018-12-05 at 23:37 +0800, Weiping Zhang wrote:
> @@ -130,7 +119,7 @@ void blk_add_timer(struct request *req)
>* than an existing one, modify the timer. Round up to next nearest
>* second.
>*/
> - expiry = blk_rq_timeout(round_jiffies_up(expiry));
> + expiry
Since io_timeout was added to sysfs, the user can tune timeouts
by that attribute, so kill this limitation.
Signed-off-by: Weiping Zhang
---
block/blk-timeout.c | 13 +
block/blk.h | 4
2 files changed, 1 insertion(+), 16 deletions(-)
diff --git a/block/blk-timeout.c